Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    questions about personal experiences and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    521
    -0.16
    onet
    -0.15
     Semaphore
    -0.14
     demonstr
    -0.14
    IBC
    -0.14
     Conservation
    -0.14
    iset
    -0.14
    abwe
    -0.13
    NUM
    -0.13
     ACC
    -0.13
    POSITIVE LOGITS
     McD
    0.16
    emek
    0.15
    paque
    0.15
     LEGO
    0.14
     EGL
    0.14
    APPLE
    0.14
    odata
    0.14
    ìķĦìĦľ
    0.13
    ulfilled
    0.13
    ystate
    0.13
    Act Density 0.080%

    No Known Activations